One Versus all for deep Neural Network Incertitude (OVNNI) quantification

06/01/2020
by   Gianni Franchi, et al.
22

Deep neural networks (DNNs) are powerful learning models yet their results are not always reliable. This is due to the fact that modern DNNs are usually uncalibrated and we cannot characterize their epistemic uncertainty. In this work, we propose a new technique to quantify the epistemic uncertainty of data easily. This method consists in mixing the predictions of an ensemble of DNNs trained to classify One class vs All the other classes (OVA) with predictions from a standard DNN trained to perform All vs All (AVA) classification. On the one hand, the adjustment provided by the AVA DNN to the score of the base classifiers allows for a more fine-grained inter-class separation. On the other hand, the two types of classifiers enforce mutually their detection of out-of-distribution (OOD) samples, circumventing entirely the requirement of using such samples during training. Our method achieves state of the art performance in quantifying OOD data across multiple datasets and architectures while requiring little hyper-parameter tuning.

READ FULL TEXT

page 14

page 15

research
08/13/2021

Detecting OODs as datapoints with High Uncertainty

Deep neural networks (DNNs) are known to produce incorrect predictions w...
research
02/24/2021

Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks

In order to safely deploy Deep Neural Networks (DNNs) within the percept...
research
08/24/2020

SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates

Uncertainty quantification is a fundamental yet unsolved problem for dee...
research
09/21/2018

Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems

Physics-informed neural networks (PINNs) have recently emerged as an alt...
research
08/13/2019

Learning Credible Deep Neural Networks with Rationale Regularization

Recent explainability related studies have shown that state-of-the-art D...
research
05/25/2023

Neural (Tangent Kernel) Collapse

This work bridges two important concepts: the Neural Tangent Kernel (NTK...
research
04/16/2021

Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty

Learning methods for relative camera pose estimation have been developed...

Please sign up or login with your details

Forgot password? Click here to reset